tf.feature_column.numeric_column
tf.feature_column.numeric_column
tf.feature_column.numeric_column
numeric_column( key, shape=(1,), default_value=None, dtype=tf.float32, normalizer_fn=None )
Defined in tensorflow/python/feature_column/feature_column.py
.
Represents real valued or numerical features.
Example:
price = numeric_column('price') columns = [price, ...] features = tf.parse_example(..., features=make_parse_example_spec(columns)) dense_tensor = input_layer(features, columns) # or bucketized_price = bucketized_column(price, boundaries=[...]) columns = [bucketized_price, ...] features = tf.parse_example(..., features=make_parse_example_spec(columns)) linear_prediction = linear_model(features, columns)
Args:
-
key
: A unique string identifying the input feature. It is used as the column name and the dictionary key for feature parsing configs, featureTensor
objects, and feature columns. -
shape
: An iterable of integers specifies the shape of theTensor
. An integer can be given which means a single dimensionTensor
with given width. TheTensor
representing the column will have the shape of [batch_size] +shape
. -
default_value
: A single value compatible withdtype
or an iterable of values compatible withdtype
which the column takes on duringtf.Example
parsing if data is missing. A default value ofNone
will causetf.parse_example
to fail if an example does not contain this column. If a single value is provided, the same value will be applied as the default value for every item. If an iterable of values is provided, the shape of thedefault_value
should be equal to the givenshape
. -
dtype
: defines the type of values. Default value istf.float32
. Must be a non-quantized, real integer or floating point type. -
normalizer_fn
: If notNone
, a function that can be used to normalize the value of the tensor afterdefault_value
is applied for parsing. Normalizer function takes the inputTensor
as its argument, and returns the outputTensor
. (e.g. lambda x: (x - 3.0) / 4.2). Please note that even though the most common use case of this function is normalization, it can be used for any kind of Tensorflow transformations.
Returns:
A _NumericColumn
.
Raises:
-
TypeError
: if any dimension in shape is not an int -
ValueError
: if any dimension in shape is not a positive integer -
TypeError
: ifdefault_value
is an iterable but not compatible withshape
-
TypeError
: ifdefault_value
is not compatible withdtype
. -
ValueError
: ifdtype
is not convertible totf.float32
.
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/feature_column/numeric_column